LATIDIA · Ciberseguridad

Elevando el listón para la seguridad de los adolescentes chinos LLM: un punto de referencia culturalmente fundamentado y de grano fino

arXiv:2609.35902v1 Anuncio Tipo: nuevo Resumen: Los riesgos de seguridad en las conversaciones con adolescentes no siempre son explícitos. Una solicitud puede parecer inofensiva a menos que un modelo considere la edad del usuario, las circunstancias y los antecedentes.

La noticia

arXiv:2609.35902v1 Announce Type: new Abstract: Safety risks in conversations with adolescents are not always explicit. A request may appear harmless unless a model considers the user's age, circumstances, and earlier turns. Existing Chinese safety benchmarks mainly target general users and give limited attention to adolescent safety. Single-turn tests also miss risks that emerge over several turns. QH-Bench is a Chinese-language benchmark for adolescent content safety, with scenarios grounded in Chinese social and cultural settings. The single-turn track contains 715 test items organized into 10 risk domains, 50 subdomains, and 143 fine-grained risk scenarios. The multi-turn track contains 100 four-turn trajectories in a balanced 10-by-10 design that combines the same ten